{"id":"https://openalex.org/W3096980367","doi":"https://doi.org/10.21437/interspeech.2020-1072","title":"A Cyclical Post-Filtering Approach to Mismatch Refinement of Neural Vocoder for Text-to-Speech Systems","display_name":"A Cyclical Post-Filtering Approach to Mismatch Refinement of Neural Vocoder for Text-to-Speech Systems","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096980367","doi":"https://doi.org/10.21437/interspeech.2020-1072","mag":"3096980367"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1072","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037001032","display_name":"Yi-Chiao Wu","orcid":"https://orcid.org/0000-0003-4390-1354"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yi-Chiao Wu","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050897938","display_name":"Patrick Lumban Tobing","orcid":"https://orcid.org/0000-0003-2792-8418"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Patrick Lumban Tobing","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042575973","display_name":"Kazuki Yasuhara","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuki Yasuhara","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034982023","display_name":"Noriyuki Matsunaga","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Noriyuki Matsunaga","raw_affiliation_strings":["AI, Inc., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI, Inc., Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018533235","display_name":"Yamato Ohtani","orcid":"https://orcid.org/0009-0009-2961-2821"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yamato Ohtani","raw_affiliation_strings":["AI, Inc., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI, Inc., Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Information Technology Center, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3540","last_page":"3544"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7382546663284302},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6822384595870972},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4977445900440216},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.424924373626709},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41233140230178833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3386123776435852}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7382546663284302},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6822384595870972},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4977445900440216},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.424924373626709},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41233140230178833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3386123776435852}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1072","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1688345242","display_name":"Next generation speech translation research","funder_award_id":"17H06101","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6718509927","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7789893098","display_name":null,"funder_award_id":"JP-MJCR19A3","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1502723613","https://openalex.org/W1778816975","https://openalex.org/W2049036695","https://openalex.org/W2120605154","https://openalex.org/W2400063444","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2666408839","https://openalex.org/W2746474733","https://openalex.org/W2746654391","https://openalex.org/W2747161606","https://openalex.org/W2749651610","https://openalex.org/W2786868129","https://openalex.org/W2797310469","https://openalex.org/W2802935216","https://openalex.org/W2887511658","https://openalex.org/W2903365642","https://openalex.org/W2911540263","https://openalex.org/W2936002583","https://openalex.org/W2937918341","https://openalex.org/W2963103134","https://openalex.org/W2963341071","https://openalex.org/W2963411216","https://openalex.org/W2963975282","https://openalex.org/W2964243274","https://openalex.org/W3014786045","https://openalex.org/W3041738652","https://openalex.org/W4251158933","https://openalex.org/W4294619240","https://openalex.org/W4320013936"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W4253660971","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469"],"abstract_inverted_index":{"Recently,":[0],"the":[1,19,45,104,108,126,148,151],"effectiveness":[2,149],"of":[3,107,150],"text-to-speech":[4],"(TTS)":[5],"systems":[6,27,118],"combined":[7],"with":[8,129],"neural":[9,41,105,120],"vocoders":[10],"to":[11,38,43,89,115],"generate":[12,90],"high-fidelity":[13],"speech":[14,46],"has":[15],"been":[16],"shown.However,":[17],"collecting":[18],"required":[20],"training":[21,74,96],"data":[22,94,101],"and":[23,32,66,69,75,97,119,140,143],"building":[24],"these":[25,79],"advanced":[26],"from":[28,58],"scratch":[29],"are":[30],"time":[31],"resource":[33],"consuming.An":[34],"economical":[35],"approach":[36,55],"is":[37],"develop":[39],"a":[40,83,130],"vocoder":[42,133],"enhance":[44],"generated":[47],"by":[48],"existing":[49],"or":[50],"low-cost":[51],"TTS":[52,65,117,138],"systems.Nonetheless,":[53],"this":[54,110,122],"usually":[56],"suffers":[57],"two":[59,135],"issues:":[60],"1)":[61],"temporal":[62],"mismatches":[63,72],"between":[64,73],"natural":[67],"waveforms":[68],"2)":[70],"acoustic":[71],"testing":[76,103],"data.To":[77],"address":[78],"issues,":[80],"we":[81,124],"adopt":[82],"cyclic":[84],"voice":[85],"conversion":[86],"(VC)":[87],"model":[88],"temporally":[91],"matched":[92,99],"pseudo-VC":[93],"for":[95,102,134],"acoustically":[98],"enhanced":[100],"vocoders.Because":[106],"generality,":[109],"framework":[111],"can":[112],"be":[113],"applied":[114],"arbitrary":[116],"vocoders.In":[121],"paper,":[123],"apply":[125],"proposed":[127,152],"method":[128],"state-of-the-art":[131],"WaveNet":[132],"different":[136],"basic":[137],"systems,":[139],"both":[141],"objective":[142],"subjective":[144],"experimental":[145],"results":[146],"confirm":[147],"framework.":[153]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}